Research map / Image generation / Super-resolution
A Generalized Tensor Formulation for Hyperspectral Image Super-Resolution Under General Spatial Blurring
Yinjian Wang, Wei Li, Yuanyuan Gui, Qian Du, James E. Fowler
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use generalized tensor formulation with blockwise group sparsity instead of CSTF | tensor-based HSR · Houston2013 AGK4 (non-blind) | PSNR (dB): 33.1642 -> 49.1804 | Improved |
| use generalized tensor formulation instead of CSTF | tensor-based HSR · Houston2013 AGK3 (non-blind) | PSNR (dB): 37.8331 -> 49.1722 | Improved |
| use generalized tensor formulation instead of CSTF | tensor-based HSR · Houston2013 AGK1 (non-blind) | PSNR (dB): 48.4274 -> 49.3079 | Improved |
| use generalized tensor formulation instead of CSTF | tensor-based HSR · URBAN (IGK, non-blind) | PSNR (dB): 44.2222 -> 45.4533 | Improved |
| increase rank of anisotropic blurring kernel from AGK1 to AGK4 | CSTF (TF-based) · Houston2013 (non-blind) | PSNR (dB): 48.4274 -> 33.1642 | Hurt |
| increase rank of anisotropic blurring kernel from AGK1 to AGK4 | BGS-GTF-HSR · Houston2013 (non-blind) | PSNR (dB): 49.3079 -> 49.1804 | No clear effect |
| use blind (estimated degradation) instead of known degradation | CSTF · Houston2013 AGK4 | PSNR (dB): 33.1642 -> 40.5917 | Improved |
| use blind (estimated degradation) instead of known degradation | BGS-GTF-HSR · URBAN (IGK) | PSNR (dB): 45.4533 -> 44.6240 | Hurt |
| use blind (estimated degradation) instead of known degradation | CSTF · Houston2013 AGK1 | PSNR (dB): 48.4274 -> 46.8317 | Hurt |
Closest papers by meaning
- Hyperspectral Image Super-Resolution via Non-Local Sparse Tensor Factorization (CVPR 2017 · similarity 0.90)
- Non-local Meets Global: An Integrated Paradigm for Hyperspectral Image Restoration (TPAMI 2020 · similarity 0.89)
- Non-Local Meets Global: An Integrated Paradigm for Hyperspectral Denoising (CVPR 2019 · similarity 0.88)
- Hyper-Laplacian Regularized Unidirectional Low-Rank Tensor Recovery for Multispectral Image Denoising (CVPR 2017 · similarity 0.88)
- S2CycleDiff: Spatial-Spectral-Bilateral Cycle-Diffusion Framework for Hyperspectral Image Super-resolution (AAAI 2024 · similarity 0.87)
- EigenSR: Eigenimage-Bridged Pre-Trained RGB Learners for Single Hyperspectral Image Super-Resolution (AAAI 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
